An Industrial Multilevel Knowledge Graph-Based Local-Global Monitoring for Plant-Wide Processes

In order to satisfy safety requirements of modern plant-wide processes, multiblock-based distributed monitoring strategies are often used to obtain higher monitoring performance, and their two critical issues refer to suitable multiblock partition for reducing uncertainties and local-global fault interpret perception for practical physical meaning. To handle these problems, a novel multilevel knowledge-graph (MLKG) based on combining domain expert knowledge and monitoring data are constructed to describe characteristics of plant-wide processes. And then numerous monitoring variables of each node (block) can be used to calculate the node status which can be used to realize fault detection by exceeding corresponding thresholds. Creatively, numerous node statuses of multilevel can be aggregated into the top-level node status to globally characterize the system health to realize fault detection. Finally, methods such as variables contribute rate can be adopted to locally locate the fault to achieve fault location, which can be regarded as an attempt to interpret the fault detection results. Results of benchmark and practical-case-application can be used to demonstrate the effectiveness and applicability of this proposed method.